Skip to content

N
NiuTrans.Tensor
Commit 137df5d9 by liyinqiao
Options

Merge with HU Chi branch. 

1. Offer global setting for enableGrad.
2. Update XList.
3. Minor error fixed.
parent b3dfbdcd
正在显示 包含 260 行增加 和 280 行删除
source/tensor/XCall.h
...@@ -26,6 +26,9 @@ ...@@ -26,6 +26,9 @@
namespace nts { // namespace nts(NiuTrans.Tensor) namespace nts { // namespace nts(NiuTrans.Tensor)
/* default settings */
#define X_ENABLE_GRAD false
/* /*
* we define the "new and delete" functions below * we define the "new and delete" functions below
*/ */
...@@ -38,13 +41,13 @@ void InitTensorV2(XTensor * tensor, ...@@ -38,13 +41,13 @@ void InitTensorV2(XTensor * tensor,
/* initialize a dense XTensor */ /* initialize a dense XTensor */
void InitTensor(XTensor * tensor, void InitTensor(XTensor * tensor,
const int myOrder, const int * myDimSize, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myOrder, const int * myDimSize, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a scalar V2 */ /* initialize a scalar V2 */
void InitTensor0DV2(XTensor * tensor, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, XMem * myMem = NULL); void InitTensor0DV2(XTensor * tensor, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, XMem * myMem = NULL);
/* initialize a scalar */ /* initialize a scalar */
void InitTensor0D(XTensor * tensor, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); void InitTensor0D(XTensor * tensor, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a dense vector V2 */ /* initialize a dense vector V2 */
void InitTensor1DV2(XTensor * tensor, const int num, void InitTensor1DV2(XTensor * tensor, const int num,
...@@ -52,7 +55,7 @@ void InitTensor1DV2(XTensor * tensor, const int num, ...@@ -52,7 +55,7 @@ void InitTensor1DV2(XTensor * tensor, const int num,
/* initialize a dense vector */ /* initialize a dense vector */
void InitTensor1D(XTensor * tensor, const int num, void InitTensor1D(XTensor * tensor, const int num,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a dense matrix V2 */ /* initialize a dense matrix V2 */
void InitTensor2DV2(XTensor * tensor, const int rowNum, const int colNum, void InitTensor2DV2(XTensor * tensor, const int rowNum, const int colNum,
...@@ -60,7 +63,7 @@ void InitTensor2DV2(XTensor * tensor, const int rowNum, const int colNum, ...@@ -60,7 +63,7 @@ void InitTensor2DV2(XTensor * tensor, const int rowNum, const int colNum,
/* initialize a dense matrix */ /* initialize a dense matrix */
void InitTensor2D(XTensor * tensor, const int rowNum, const int colNum, void InitTensor2D(XTensor * tensor, const int rowNum, const int colNum,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a dense 3d tensor V2 */ /* initialize a dense 3d tensor V2 */
void InitTensor3DV2(XTensor * tensor, const int d0, const int d1, const int d2, void InitTensor3DV2(XTensor * tensor, const int d0, const int d1, const int d2,
...@@ -68,7 +71,7 @@ void InitTensor3DV2(XTensor * tensor, const int d0, const int d1, const int d2, ...@@ -68,7 +71,7 @@ void InitTensor3DV2(XTensor * tensor, const int d0, const int d1, const int d2,
/* initialize a dense 3d tensor */ /* initialize a dense 3d tensor */
void InitTensor3D(XTensor * tensor, const int d0, const int d1, const int d2, void InitTensor3D(XTensor * tensor, const int d0, const int d1, const int d2,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a dense 4d tensor V2 */ /* initialize a dense 4d tensor V2 */
void InitTensor4DV2(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, void InitTensor4DV2(XTensor * tensor, const int d0, const int d1, const int d2, const int d3,
...@@ -76,7 +79,7 @@ void InitTensor4DV2(XTensor * tensor, const int d0, const int d1, const int d2, ...@@ -76,7 +79,7 @@ void InitTensor4DV2(XTensor * tensor, const int d0, const int d1, const int d2,
/* initialize a dense 4d tensor */ /* initialize a dense 4d tensor */
void InitTensor4D(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, void InitTensor4D(XTensor * tensor, const int d0, const int d1, const int d2, const int d3,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a dense 5d tensor V2 */ /* initialize a dense 5d tensor V2 */
void InitTensor5DV2(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, const int d4, void InitTensor5DV2(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, const int d4,
...@@ -84,7 +87,7 @@ void InitTensor5DV2(XTensor * tensor, const int d0, const int d1, const int d2, ...@@ -84,7 +87,7 @@ void InitTensor5DV2(XTensor * tensor, const int d0, const int d1, const int d2,
/* initialize a dense 5d tensor */ /* initialize a dense 5d tensor */
void InitTensor5D(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, const int d4, void InitTensor5D(XTensor * tensor, const int d0, const int d1, const int d2, const int d3, const int d4,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* initialize a tensor with a reference tensor V2 */ /* initialize a tensor with a reference tensor V2 */
void InitTensorV2(XTensor * tensor, const XTensor * reference); void InitTensorV2(XTensor * tensor, const XTensor * reference);
...@@ -104,7 +107,7 @@ XTensor * NewTensorV2(const int myOrder, const int * myDimSize, const TENSOR_DAT ...@@ -104,7 +107,7 @@ XTensor * NewTensorV2(const int myOrder, const int * myDimSize, const TENSOR_DAT
/* generate a dense XTensor */ /* generate a dense XTensor */
XTensor * NewTensor(const int myOrder, const int * myDimSize, const TENSOR_DATA_TYPE myDataType = X_FLOAT, XTensor * NewTensor(const int myOrder, const int * myDimSize, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a XTensor which allocates data on the buffer V2 */ /* generate a XTensor which allocates data on the buffer V2 */
XTensor * NewTensorBufV2(const int myOrder, const int * myDimSize, XTensor * NewTensorBufV2(const int myOrder, const int * myDimSize,
...@@ -113,26 +116,26 @@ XTensor * NewTensorBufV2(const int myOrder, const int * myDimSize, ...@@ -113,26 +116,26 @@ XTensor * NewTensorBufV2(const int myOrder, const int * myDimSize,
/* generate a dense XTensor which allocates data on the buffer */ /* generate a dense XTensor which allocates data on the buffer */
XTensor * NewTensorBuf(const int myOrder, const int * myDimSize, XTensor * NewTensorBuf(const int myOrder, const int * myDimSize,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a XTensor which allocates data on the buffer V2 */ /* generate a XTensor which allocates data on the buffer V2 */
XTensor * NewTensorBufV2(const XTensor * reference, int devID, XMem * myMem); XTensor * NewTensorBufV2(const XTensor * reference, int devID, XMem * myMem);
/* generate a XTensor which allocates data on the buffer */ /* generate a XTensor which allocates data on the buffer */
XTensor * NewTensorBuf(const XTensor * reference, int devID, const bool isEnableGrad = true); XTensor * NewTensorBuf(const XTensor * reference, int devID, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a scalar V2 */ /* generate a scalar V2 */
XTensor * NewTensor0DV2(const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, XMem * myMem = NULL); XTensor * NewTensor0DV2(const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, XMem * myMem = NULL);
/* generate a scalar */ /* generate a scalar */
XTensor * NewTensor0D(const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); XTensor * NewTensor0D(const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense vector V2 */ /* generate a dense vector V2 */
XTensor * NewTensor1DV2(const int num, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, XTensor * NewTensor1DV2(const int num, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1,
XMem * myMem = NULL); XMem * myMem = NULL);
/* generate a dense vector */ /* generate a dense vector */
XTensor * NewTensor1D(const int num, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = true); XTensor * NewTensor1D(const int num, const TENSOR_DATA_TYPE myDataType = X_FLOAT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense matrix V2 */ /* generate a dense matrix V2 */
XTensor * NewTensor2DV2(const int rowNum, const int colNum, XTensor * NewTensor2DV2(const int rowNum, const int colNum,
...@@ -142,7 +145,7 @@ XTensor * NewTensor2DV2(const int rowNum, const int colNum, ...@@ -142,7 +145,7 @@ XTensor * NewTensor2DV2(const int rowNum, const int colNum,
/* generate a dense matrix */ /* generate a dense matrix */
XTensor * NewTensor2D(const int rowNum, const int colNum, XTensor * NewTensor2D(const int rowNum, const int colNum,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense 3d tensor V2 */ /* generate a dense 3d tensor V2 */
XTensor * NewTensor3DV2(const int d0, const int d1, const int d2, XTensor * NewTensor3DV2(const int d0, const int d1, const int d2,
...@@ -152,7 +155,7 @@ XTensor * NewTensor3DV2(const int d0, const int d1, const int d2, ...@@ -152,7 +155,7 @@ XTensor * NewTensor3DV2(const int d0, const int d1, const int d2,
/* generate a dense 3d tensor */ /* generate a dense 3d tensor */
XTensor * NewTensor3D(const int d0, const int d1, const int d2, XTensor * NewTensor3D(const int d0, const int d1, const int d2,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense 4d tensor V2 */ /* generate a dense 4d tensor V2 */
XTensor * NewTensor4DV2(const int d0, const int d1, const int d2, const int d3, XTensor * NewTensor4DV2(const int d0, const int d1, const int d2, const int d3,
...@@ -162,7 +165,7 @@ XTensor * NewTensor4DV2(const int d0, const int d1, const int d2, const int d3, ...@@ -162,7 +165,7 @@ XTensor * NewTensor4DV2(const int d0, const int d1, const int d2, const int d3,
/* generate a dense 4d tensor */ /* generate a dense 4d tensor */
XTensor * NewTensor4D(const int d0, const int d1, const int d2, const int d3, XTensor * NewTensor4D(const int d0, const int d1, const int d2, const int d3,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense 5d tensor V2 */ /* generate a dense 5d tensor V2 */
XTensor * NewTensor5DV2(const int d0, const int d1, const int d2, const int d3, const int d4, XTensor * NewTensor5DV2(const int d0, const int d1, const int d2, const int d3, const int d4,
...@@ -172,10 +175,10 @@ XTensor * NewTensor5DV2(const int d0, const int d1, const int d2, const int d3, ...@@ -172,10 +175,10 @@ XTensor * NewTensor5DV2(const int d0, const int d1, const int d2, const int d3,
/* generate a dense 5d tensor */ /* generate a dense 5d tensor */
XTensor * NewTensor5D(const int d0, const int d1, const int d2, const int d3, const int d4, XTensor * NewTensor5D(const int d0, const int d1, const int d2, const int d3, const int d4,
const TENSOR_DATA_TYPE myDataType = X_FLOAT, const TENSOR_DATA_TYPE myDataType = X_FLOAT,
const int myDevID = -1, const bool isEnableGrad = true); const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a dense vector by range */ /* generate a dense vector by range */
XTensor * NewTensorRange(int lower, int upper, int step, const TENSOR_DATA_TYPE myDataType = X_INT, const int myDevID = -1, const bool isEnableGrad = true); XTensor * NewTensorRange(int lower, int upper, int step, const TENSOR_DATA_TYPE myDataType = X_INT, const int myDevID = -1, const bool isEnableGrad = X_ENABLE_GRAD);
/* generate a copy of XTensor (with a reference to a given tensor) */ /* generate a copy of XTensor (with a reference to a given tensor) */
XTensor * NewTensor(const XTensor * a, bool isFilledData = true); XTensor * NewTensor(const XTensor * a, bool isFilledData = true);
......
source/tensor/XList.cpp
...@@ -249,26 +249,6 @@ inline int TensorListBase<T>::FindFirst(const T& item) ...@@ -249,26 +249,6 @@ inline int TensorListBase<T>::FindFirst(const T& item)
return -1; return -1;
} }
template <>
inline int TensorListBase<Example>::FindFirst(const Example& item)
{
for (int i = 0; i < count; i++) {
if (item.id == items[i].id)
return i;
}
return -1;
}
template <>
inline int TensorListBase<Result>::FindFirst(const Result& item)
{
for (int i = 0; i < count; i++) {
if (item.id == items[i].id)
return i;
}
return -1;
}
/* clear the data array */ /* clear the data array */
template <typename T> template <typename T>
void TensorListBase<T>::Clear() void TensorListBase<T>::Clear()
...@@ -383,8 +363,7 @@ template struct TensorListBase<long>; ...@@ -383,8 +363,7 @@ template struct TensorListBase<long>;
template struct TensorListBase<float>; template struct TensorListBase<float>;
template struct TensorListBase<short>; template struct TensorListBase<short>;
template struct TensorListBase<XTensor*>; template struct TensorListBase<XTensor*>;
template struct TensorListBase<Result>; template struct TensorListBase<uint64_t>;
template struct TensorListBase<Example>;
template struct TensorListBase<void*>; template struct TensorListBase<void*>;
} /* end of the nts (NiuTrans.Tensor) namespace */ } /* end of the nts (NiuTrans.Tensor) namespace */
\ No newline at end of file
source/tensor/XList.h
...@@ -26,6 +26,8 @@ ...@@ -26,6 +26,8 @@
#include "XMem.h" #include "XMem.h"
#include "XGlobal.h" #include "XGlobal.h"
#include <cstdint>
#ifndef __TensorList_H__ #ifndef __TensorList_H__
#define __TensorList_H__ #define __TensorList_H__
...@@ -118,7 +120,14 @@ public: ...@@ -118,7 +120,14 @@ public:
void Shuffle(int nround = 10, int beg = -1, int len = 0); void Shuffle(int nround = 10, int beg = -1, int len = 0);
/* short */ /* short */
T& operator[] (int i) { return GetItem(i); }; T& operator[] (int i) {
CheckNTErrors(i >= -count && i < count, "Index of a list item is out of scope!");
CheckNTErrors(count > 0, "Cannt index the item in an empty list!");
if (i < 0)
return items[count + i];
else
return items[i];
};
T& Get(int i) { return GetItem(i); }; T& Get(int i) { return GetItem(i); };
void Set(int i, T item) { SetItem(i, item); }; void Set(int i, T item) { SetItem(i, item); };
}; };
...@@ -132,19 +141,7 @@ typedef TensorListBase<char*> StrList; ...@@ -132,19 +141,7 @@ typedef TensorListBase<char*> StrList;
typedef TensorListBase<long> LongList; typedef TensorListBase<long> LongList;
typedef TensorListBase<float> FloatList; typedef TensorListBase<float> FloatList;
typedef TensorListBase<short> ShortList; typedef TensorListBase<short> ShortList;
typedef TensorListBase<uint64_t> UInt64List;
struct Example {
int id;
IntList data;
};
struct Result {
int id;
IntList data;
};
typedef TensorListBase<Result> ResultList;
typedef TensorListBase<Example> ExampleList;
typedef TensorListBase<XTensor*> TensorList; typedef TensorListBase<XTensor*> TensorList;
} /* end of the nts (NiuTrans.Tensor) namespace */ } /* end of the nts (NiuTrans.Tensor) namespace */
......
source/tensor/XTensor.cpp
...@@ -64,7 +64,7 @@ ...@@ -64,7 +64,7 @@
#endif #endif
/* the nts (NiuTrans.Tensor) namespace */ /* the nts (NiuTrans.Tensor) namespace */
namespace nts{ namespace nts {
int tensorIDGlobal = 0; int tensorIDGlobal = 0;
MUTEX_HANDLE tensorMutex; MUTEX_HANDLE tensorMutex;
...@@ -73,11 +73,11 @@ XTensor NULLTensor; ...@@ -73,11 +73,11 @@ XTensor NULLTensor;
/* generate a tensor id */ /* generate a tensor id */
int MakeTensorID() int MakeTensorID()
{ {
if(tensorIDGlobal == 0) if (tensorIDGlobal == 0)
MUTEX_INIT(tensorMutex); MUTEX_INIT(tensorMutex);
MUTEX_LOCK(tensorMutex); MUTEX_LOCK(tensorMutex);
int id = tensorIDGlobal++; int id = tensorIDGlobal++;
MUTEX_UNLOCK(tensorMutex); MUTEX_UNLOCK(tensorMutex);
return id; return id;
...@@ -91,13 +91,13 @@ XTensor::XTensor() ...@@ -91,13 +91,13 @@ XTensor::XTensor()
id = MakeTensorID(); id = MakeTensorID();
isDefaultDType = true; isDefaultDType = true;
isInGlobalMem = false; isInGlobalMem = false;
isInit = false; isInit = false;
isTmp = false; isTmp = false;
} }
/* constructor */ /* constructor */
XTensor::XTensor(const XTensor * reference) XTensor::XTensor(const XTensor* reference)
{ {
Init(); Init();
SetDataPointer(); SetDataPointer();
...@@ -112,7 +112,7 @@ constructor ...@@ -112,7 +112,7 @@ constructor
>> myDevID - device id >> myDevID - device id
>> myMem - memory pool used to allocating the data array >> myMem - memory pool used to allocating the data array
*/ */
XTensor::XTensor(const int myOrder, int myDevID, XMem * myMem) XTensor::XTensor(const int myOrder, int myDevID, XMem* myMem)
{ {
CheckNTErrors((myOrder >= 0), "Illegal tensor order!"); CheckNTErrors((myOrder >= 0), "Illegal tensor order!");
...@@ -134,8 +134,8 @@ constructor ...@@ -134,8 +134,8 @@ constructor
>> myDevID - device id >> myDevID - device id
>> myMem - memory pool used to allocating the data array >> myMem - memory pool used to allocating the data array
*/ */
XTensor::XTensor(const int myOrder, const int * myDimSize, const TENSOR_DATA_TYPE myDataType, XTensor::XTensor(const int myOrder, const int* myDimSize, const TENSOR_DATA_TYPE myDataType,
const float myDenseRatio, int myDevID, XMem * myMem) const float myDenseRatio, int myDevID, XMem* myMem)
{ {
Init(); Init();
SetDataPointer(); SetDataPointer();
...@@ -145,12 +145,12 @@ XTensor::XTensor(const int myOrder, const int * myDimSize, const TENSOR_DATA_TYP ...@@ -145,12 +145,12 @@ XTensor::XTensor(const int myOrder, const int * myDimSize, const TENSOR_DATA_TYP
mem = myMem; mem = myMem;
devID = myMem != NULL ? myMem->devID : myDevID; devID = myMem != NULL ? myMem->devID : myDevID;
if(order >= 0) if (order >= 0)
Resize(myOrder, myDimSize, myDataType, myDenseRatio); Resize(myOrder, myDimSize, myDataType, myDenseRatio);
} }
/* copy constructor */ /* copy constructor */
XTensor::XTensor(const XTensor &reference) XTensor::XTensor(const XTensor& reference)
{ {
Init(); Init();
SetDataPointer(); SetDataPointer();
...@@ -158,8 +158,8 @@ XTensor::XTensor(const XTensor &reference) ...@@ -158,8 +158,8 @@ XTensor::XTensor(const XTensor &reference)
ShallowCopy(reference); ShallowCopy(reference);
data = NULL; data = NULL;
dataHost = NULL; dataHost = NULL;
if(reference.isTmp){ if (reference.isTmp) {
devID = reference.devID; devID = reference.devID;
mem = reference.mem; mem = reference.mem;
data = reference.data; data = reference.data;
...@@ -172,26 +172,26 @@ XTensor::XTensor(const XTensor &reference) ...@@ -172,26 +172,26 @@ XTensor::XTensor(const XTensor &reference)
This is VERY tricky and there might be better solutions :) */ This is VERY tricky and there might be better solutions :) */
*reference.dataP = NULL; *reference.dataP = NULL;
} }
else{ else {
devID = reference.devID; devID = reference.devID;
mem = reference.mem; mem = reference.mem;
InitTensorV2(this, &reference); InitTensorV2(this, &reference);
_CopyValues(&reference, this); _CopyValues(&reference, this);
} }
if(reference.isTmp) if (reference.isTmp)
XLink::Replace(&reference, this); XLink::Replace(&reference, this);
else{ else {
CheckNTErrors(outgo.tailNum == 0, "The node has outgoing edge to other nodes!"); CheckNTErrors(outgo.tailNum == 0, "The node has outgoing edge to other nodes!");
XLink::CopyIncoming(&reference, this); XLink::CopyIncoming(&reference, this);
} }
isInit = true; isInit = true;
isTmp = reference.isTmp; isTmp = reference.isTmp;
} }
/* copy constructor (with right value reference) */ /* copy constructor (with right value reference) */
XTensor::XTensor(const XTensor &&reference) XTensor::XTensor(const XTensor&& reference)
{ {
Init(); Init();
SetDataPointer(); SetDataPointer();
...@@ -215,7 +215,7 @@ XTensor::XTensor(const XTensor &&reference) ...@@ -215,7 +215,7 @@ XTensor::XTensor(const XTensor &&reference)
XLink::Replace(&reference, this); XLink::Replace(&reference, this);
isInit = true; isInit = true;
isTmp = reference.isTmp; isTmp = reference.isTmp;
} }
/* de-constructor */ /* de-constructor */
...@@ -225,12 +225,12 @@ XTensor::~XTensor() ...@@ -225,12 +225,12 @@ XTensor::~XTensor()
the connectivity of the graph. To kill memory the connectivity of the graph. To kill memory
leak, we release the data of the new tensor leak, we release the data of the new tensor
when its parent is deleted (see ClearIncoming). */ when its parent is deleted (see ClearIncoming). */
if(outgo.tailNum > 0){ if (outgo.tailNum > 0) {
int dims[MAX_TENSOR_DIM_NUM]; int dims[MAX_TENSOR_DIM_NUM];
memcpy(dims, dimSize, order * sizeof(int)); memcpy(dims, dimSize, order * sizeof(int));
dims[0] = -dims[0]; dims[0] = -dims[0];
XTensor * newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem); XTensor* newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem);
newTensor->SetTMPFlag(); newTensor->SetTMPFlag();
newTensor->data = data; newTensor->data = data;
data = NULL; data = NULL;
...@@ -243,12 +243,12 @@ XTensor::~XTensor() ...@@ -243,12 +243,12 @@ XTensor::~XTensor()
DestroyData(); DestroyData();
if(grad != NULL) if (grad != NULL)
delete grad; delete grad;
} }
/* set the name of the tensor */ /* set the name of the tensor */
void XTensor::SetName(const char * myName) void XTensor::SetName(const char* myName)
{ {
strcpy(name, myName); strcpy(name, myName);
} }
...@@ -277,10 +277,10 @@ void XTensor::Init() ...@@ -277,10 +277,10 @@ void XTensor::Init()
isInGlobalMem = false; isInGlobalMem = false;
memset(isAllValued, 0, sizeof(bool) * MAX_TENSOR_DIM_NUM); memset(isAllValued, 0, sizeof(bool) * MAX_TENSOR_DIM_NUM);
isInit = false; isInit = false;
isTmp = false; isTmp = false;
isGrad = false; isGrad = false;
isVar = false; isVar = false;
enableGrad = true; enableGrad = X_ENABLE_GRAD;
visitMark = 0; visitMark = 0;
grad = NULL; grad = NULL;
} }
...@@ -288,16 +288,16 @@ void XTensor::Init() ...@@ -288,16 +288,16 @@ void XTensor::Init()
/* delete data arrays */ /* delete data arrays */
void XTensor::DestroyData() void XTensor::DestroyData()
{ {
if(data != NULL && mem == NULL && !isShared) if (data != NULL && mem == NULL && !isShared)
XMemFree(devID, data); XMemFree(devID, data);
else if(data != NULL && isInGlobalMem) else if (data != NULL && isInGlobalMem)
FreeData(this, mem); FreeData(this, mem);
else if(data != NULL) else if (data != NULL)
mem->Release(data, GetDataSizeInChar(), signature); mem->Release(data, GetDataSizeInChar(), signature);
data = NULL; data = NULL;
if(dataHost != NULL) if (dataHost != NULL)
delete[] (char*)dataHost; delete[] (char*)dataHost;
dataHost = NULL; dataHost = NULL;
} }
...@@ -307,7 +307,7 @@ shallow copy of the tensor ...@@ -307,7 +307,7 @@ shallow copy of the tensor
Note that we do not copy data array here Note that we do not copy data array here
>> tensor - the source tensor >> tensor - the source tensor
*/ */
void XTensor::ShallowCopy(const XTensor &tensor) void XTensor::ShallowCopy(const XTensor& tensor)
{ {
strcpy(name, tensor.name); strcpy(name, tensor.name);
order = tensor.order; order = tensor.order;
...@@ -318,7 +318,7 @@ void XTensor::ShallowCopy(const XTensor &tensor) ...@@ -318,7 +318,7 @@ void XTensor::ShallowCopy(const XTensor &tensor)
unitNum = tensor.unitNum; unitNum = tensor.unitNum;
isSparse = tensor.isSparse; isSparse = tensor.isSparse;
unitNumNonZero = tensor.unitNumNonZero; unitNumNonZero = tensor.unitNumNonZero;
denseRatio = tensor.denseRatio; denseRatio = tensor.denseRatio;
isShared = tensor.isShared; isShared = tensor.isShared;
isDefaultDType = tensor.isDefaultDType; isDefaultDType = tensor.isDefaultDType;
isInGlobalMem = tensor.isInGlobalMem; isInGlobalMem = tensor.isInGlobalMem;
...@@ -330,12 +330,12 @@ XTensor& XTensor::operator= (const XTensor& tensor) ...@@ -330,12 +330,12 @@ XTensor& XTensor::operator= (const XTensor& tensor)
{ {
/* we must make a hard copy of the tensor if it is the input /* we must make a hard copy of the tensor if it is the input
of another node. */ of another node. */
if(outgo.tailNum > 0){ if (outgo.tailNum > 0) {
int dims[MAX_TENSOR_DIM_NUM]; int dims[MAX_TENSOR_DIM_NUM];
memcpy(dims, dimSize, order * sizeof(int)); memcpy(dims, dimSize, order * sizeof(int));
dims[0] = -dims[0]; dims[0] = -dims[0];
XTensor * newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem); XTensor* newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem);
newTensor->SetTMPFlag(); newTensor->SetTMPFlag();
newTensor->data = data; newTensor->data = data;
newTensor->dataHost = dataHost; newTensor->dataHost = dataHost;
...@@ -350,35 +350,35 @@ XTensor& XTensor::operator= (const XTensor& tensor) ...@@ -350,35 +350,35 @@ XTensor& XTensor::operator= (const XTensor& tensor)
dataHost = NULL; dataHost = NULL;
} }
if(false && !tensor.isTmp){ if (false && !tensor.isTmp) {
/* NOTE: this might lead to additional data copy by Mac LLVM compilers */ /* NOTE: this might lead to additional data copy by Mac LLVM compilers */
/* we make an identity transformation here */ /* we make an identity transformation here */
if(outgo.tailNum > 0) if (outgo.tailNum > 0)
XLink::ClearOutgoing(this); XLink::ClearOutgoing(this);
XLink::ClearIncoming(this); XLink::ClearIncoming(this);
if(!_IsSameShaped(this, &tensor)) if (!_IsSameShaped(this, &tensor))
Resize(tensor.order, tensor.dimSize, tensor.dataType, tensor.denseRatio); Resize(tensor.order, tensor.dimSize, tensor.dataType, tensor.denseRatio);
_Identity(&tensor, this); _Identity(&tensor, this);
XLink::MakeLink(&tensor, NULL, this, FUNC_IDENTITY); XLink::MakeLink(&tensor, NULL, this, FUNC_IDENTITY);
} }
else{ else {
/* hard copy of the data array */ /* hard copy of the data array */
int size = unitNum * unitSize; int size = unitNum * unitSize;
if( isInit && !isSparse && !tensor.isSparse && if (isInit && !isSparse && !tensor.isSparse &&
size == tensor.unitNum * tensor.unitSize && size == tensor.unitNum * tensor.unitSize &&
((devID < 0 && tensor.devID < 0) && devID == tensor.devID) && ((devID < 0 && tensor.devID < 0) && devID == tensor.devID) &&
data != NULL) data != NULL)
{ {
XMemCopy(data, devID, tensor.data, tensor.devID, size); XMemCopy(data, devID, tensor.data, tensor.devID, size);
if(dataHost != NULL && tensor.dataHost != NULL) if (dataHost != NULL && tensor.dataHost != NULL)
XMemCopy(dataHost, -1, tensor.dataHost, tensor.devID, size); XMemCopy(dataHost, -1, tensor.dataHost, tensor.devID, size);
} }
else{ else {
DestroyData(); DestroyData();
if(!isInit){ if (!isInit) {
devID = tensor.devID; devID = tensor.devID;
mem = tensor.mem; mem = tensor.mem;
} }
...@@ -391,7 +391,7 @@ XTensor& XTensor::operator= (const XTensor& tensor) ...@@ -391,7 +391,7 @@ XTensor& XTensor::operator= (const XTensor& tensor)
ShallowCopy(tensor); ShallowCopy(tensor);
isInit = true; isInit = true;
isTmp = false; isTmp = false;
CheckNTErrors(outgo.tailNum == 0, "The node has outgoing edge to other nodes!"); CheckNTErrors(outgo.tailNum == 0, "The node has outgoing edge to other nodes!");
...@@ -407,12 +407,12 @@ XTensor& XTensor::operator= (const XTensor&& tensor) ...@@ -407,12 +407,12 @@ XTensor& XTensor::operator= (const XTensor&& tensor)
{ {
/* we must make a hard copy of the tensor if it is the input /* we must make a hard copy of the tensor if it is the input
of another node. */ of another node. */
if(outgo.tailNum > 0){ if (outgo.tailNum > 0) {
int dims[MAX_TENSOR_DIM_NUM]; int dims[MAX_TENSOR_DIM_NUM];
memcpy(dims, dimSize, order * sizeof(int)); memcpy(dims, dimSize, order * sizeof(int));
dims[0] = -dims[0]; dims[0] = -dims[0];
XTensor * newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem); XTensor* newTensor = new XTensor(order, dims, dataType, denseRatio, devID, mem);
newTensor->SetTMPFlag(); newTensor->SetTMPFlag();
newTensor->data = data; newTensor->data = data;
newTensor->dataHost = dataHost; newTensor->dataHost = dataHost;
...@@ -433,7 +433,7 @@ XTensor& XTensor::operator= (const XTensor&& tensor) ...@@ -433,7 +433,7 @@ XTensor& XTensor::operator= (const XTensor&& tensor)
isInit = true; isInit = true;
devID = tensor.devID; devID = tensor.devID;
mem = tensor.mem; mem = tensor.mem;
data = tensor.data; data = tensor.data;
signature = tensor.signature; signature = tensor.signature;
...@@ -456,7 +456,7 @@ XTensor XTensor::operator+ (const XTensor& tensor) const ...@@ -456,7 +456,7 @@ XTensor XTensor::operator+ (const XTensor& tensor) const
} }
/* overloading of the plus-sign */ /* overloading of the plus-sign */
XTensor XTensor::operator+ (const DTYPE shift) const XTensor XTensor::operator+ (const DTYPE shift) const
{ {
return ScaleAndShift(*this, 1, shift); return ScaleAndShift(*this, 1, shift);
} }
...@@ -500,7 +500,7 @@ XTensor XTensor::operator/ (const XTensor& tensor) const ...@@ -500,7 +500,7 @@ XTensor XTensor::operator/ (const XTensor& tensor) const
/* overloading of the division-sign */ /* overloading of the division-sign */
XTensor XTensor::operator/ (const DTYPE scale) const XTensor XTensor::operator/ (const DTYPE scale) const
{ {
return ScaleAndShift(*this, (DTYPE)1/scale, 0); return ScaleAndShift(*this, (DTYPE)1.0F / scale, 0);
} }
/* /*
...@@ -518,7 +518,7 @@ relocate the data on the target device ...@@ -518,7 +518,7 @@ relocate the data on the target device
>> myDevId - target device id >> myDevId - target device id
>> myMem - memory pool on the target device >> myMem - memory pool on the target device
*/ */
void XTensor::SetDevice(int myDevId, XMem * myMem) void XTensor::SetDevice(int myDevId, XMem* myMem)
{ {
if (myMem == NULL) { if (myMem == NULL) {
myMem = GMems.GetMem(myDevId); myMem = GMems.GetMem(myDevId);
...@@ -527,9 +527,9 @@ void XTensor::SetDevice(int myDevId, XMem * myMem) ...@@ -527,9 +527,9 @@ void XTensor::SetDevice(int myDevId, XMem * myMem)
isInGlobalMem = false; isInGlobalMem = false;
} }
bool XTensor::IsReduceShaped(const XTensor * a, const XTensor * b, int dim) bool XTensor::IsReduceShaped(const XTensor* a, const XTensor* b, int dim)
{ {
if(a == NULL || b == NULL) if (a == NULL || b == NULL)
return false; return false;
if ((a->order - 1) != b->order) if ((a->order - 1) != b->order)
...@@ -541,18 +541,18 @@ bool XTensor::IsReduceShaped(const XTensor * a, const XTensor * b, int dim) ...@@ -541,18 +541,18 @@ bool XTensor::IsReduceShaped(const XTensor * a, const XTensor * b, int dim)
return false; return false;
} }
else if (i >= dim) { else if (i >= dim) {
if (a->dimSize[i+1] != b->dimSize[i]) if (a->dimSize[i + 1] != b->dimSize[i])
return false; return false;
} }
} }
if(a->dataType != b->dataType) if (a->dataType != b->dataType)
return false; return false;
if(a->denseRatio != b->denseRatio) if (a->denseRatio != b->denseRatio)
return false; return false;
if(a->isSparse != b->isSparse) if (a->isSparse != b->isSparse)
return false; return false;
return true; return true;
...@@ -562,7 +562,7 @@ bool XTensor::IsReduceShaped(const XTensor * a, const XTensor * b, int dim) ...@@ -562,7 +562,7 @@ bool XTensor::IsReduceShaped(const XTensor * a, const XTensor * b, int dim)
set the size of each dimension set the size of each dimension
>> myDimSize - size of each dimension >> myDimSize - size of each dimension
*/ */
void XTensor::SetDim(int * myDimSize) void XTensor::SetDim(int* myDimSize)
{ {
for (int i = 0; i < order; i++) { for (int i = 0; i < order; i++) {
dimSize[i] = myDimSize[i]; dimSize[i] = myDimSize[i];
...@@ -579,7 +579,7 @@ int XTensor::GetDim(const int dim) const ...@@ -579,7 +579,7 @@ int XTensor::GetDim(const int dim) const
CheckNTErrors(dim >= -order, "dimenision is out of range!"); CheckNTErrors(dim >= -order, "dimenision is out of range!");
int d = dim; int d = dim;
if(dim < 0) if (dim < 0)
d = order + dim; d = order + dim;
return dimSize[d]; return dimSize[d];
...@@ -590,12 +590,12 @@ reshape the tensor ...@@ -590,12 +590,12 @@ reshape the tensor
>> myOrder - order of the tensor >> myOrder - order of the tensor
>> myDimSize - size of each dimension >> myDimSize - size of each dimension
*/ */
void XTensor::Reshape(const int myOrder, const int * myDimSize) void XTensor::Reshape(const int myOrder, const int* myDimSize)
{ {
int dims[MAX_TENSOR_DIM_NUM]; int dims[MAX_TENSOR_DIM_NUM];
int num = 1; int num = 1;
for(int i = 0; i < myOrder; i++){ for (int i = 0; i < myOrder; i++) {
num *= myDimSize[i]; num *= myDimSize[i];
dims[i] = abs(myDimSize[i]); dims[i] = abs(myDimSize[i]);
} }
...@@ -663,7 +663,7 @@ XTensor XTensor::TypeAs(const XTensor input) ...@@ -663,7 +663,7 @@ XTensor XTensor::TypeAs(const XTensor input)
/* get the number of items in the data array */ /* get the number of items in the data array */
int XTensor::GetSize() const int XTensor::GetSize() const
{ {
if(isSparse) if (isSparse)
return unitNumNonZero; return unitNumNonZero;
else else
return unitNum; return unitNum;
...@@ -672,13 +672,13 @@ int XTensor::GetSize() const ...@@ -672,13 +672,13 @@ int XTensor::GetSize() const
/* get the size of the memory space used */ /* get the size of the memory space used */
int XTensor::GetDataSizeInChar() const int XTensor::GetDataSizeInChar() const
{ {
if(isSparse){ if (isSparse) {
int num = int(unitNum * denseRatio + 1); int num = int(unitNum * denseRatio + 1);
int tupleSize = sizeof(int)+sizeof(DTYPE); int tupleSize = sizeof(int) + sizeof(DTYPE);
int size = sizeof(int) + tupleSize*(num); int size = sizeof(int) + tupleSize * (num);
return size; return size;
} }
else{ else {
return unitNum * unitSize; return unitNum * unitSize;
} }
} }
...@@ -690,15 +690,15 @@ get unit size in terms of "dataType" ...@@ -690,15 +690,15 @@ get unit size in terms of "dataType"
*/ */
int XTensor::GetUnitSize(TENSOR_DATA_TYPE myDataType) const int XTensor::GetUnitSize(TENSOR_DATA_TYPE myDataType) const
{ {
if(myDataType == X_INT) if (myDataType == X_INT)
return sizeof(int); return sizeof(int);
else if(myDataType == X_FLOAT) else if (myDataType == X_FLOAT)
return sizeof(float); return sizeof(float);
else if(myDataType == X_DOUBLE) else if (myDataType == X_DOUBLE)
return sizeof(double); return sizeof(double);
else if(myDataType == X_INT8) else if (myDataType == X_INT8)
return 1; return 1;
else if(myDataType == X_FLOAT16) else if (myDataType == X_FLOAT16)
return 2; return 2;
return sizeof(float); return sizeof(float);
} }
...@@ -737,21 +737,21 @@ MTYPE XTensor::GetOffset3D(int d0, int d1, int d2) const ...@@ -737,21 +737,21 @@ MTYPE XTensor::GetOffset3D(int d0, int d1, int d2) const
a vector with all entries of 0 a vector with all entries of 0
>> stream - stream for the job pipeline >> stream - stream for the job pipeline
*/ */
void XTensor::SetZeroAll(XStream * stream) void XTensor::SetZeroAll(XStream* stream)
{ {
if(data == NULL) if (data == NULL)
return; return;
if(isSparse){ if (isSparse) {
if(devID >= 0){ if (devID >= 0) {
#ifdef USE_CUDA #ifdef USE_CUDA
int size = sizeof(int) + (sizeof(int)+sizeof(DTYPE)) * unitNumNonZero; int size = sizeof(int) + (sizeof(int) + sizeof(DTYPE)) * unitNumNonZero;
int devIDBackup = 0; int devIDBackup = 0;
cudaGetDevice(&devIDBackup); cudaGetDevice(&devIDBackup);
cudaSetDevice(devID); cudaSetDevice(devID);
if(stream == NULL) if (stream == NULL)
cudaMemset(data, 0, size); cudaMemset(data, 0, size);
else else
cudaMemsetAsync(data, 0, size, stream->stream); cudaMemsetAsync(data, 0, size, stream->stream);
...@@ -764,14 +764,14 @@ void XTensor::SetZeroAll(XStream * stream) ...@@ -764,14 +764,14 @@ void XTensor::SetZeroAll(XStream * stream)
unitNumNonZero = 0; unitNumNonZero = 0;
} }
else{ else {
if(devID >= 0){ if (devID >= 0) {
#ifdef USE_CUDA #ifdef USE_CUDA
int devIDBackup = 0; int devIDBackup = 0;
cudaGetDevice(&devIDBackup); cudaGetDevice(&devIDBackup);
cudaSetDevice(devID); cudaSetDevice(devID);
if(stream == NULL) if (stream == NULL)
cudaMemset(data, 0, unitNum * unitSize); cudaMemset(data, 0, unitNum * unitSize);
else else
cudaMemsetAsync(data, 0, unitNum * unitSize, stream->stream); cudaMemsetAsync(data, 0, unitNum * unitSize, stream->stream);
...@@ -789,9 +789,9 @@ void XTensor::SetZeroAll(XStream * stream) ...@@ -789,9 +789,9 @@ void XTensor::SetZeroAll(XStream * stream)
>> num - number of data items >> num - number of data items
>> beg - where we start the data copy in the data array of the tensor >> beg - where we start the data copy in the data array of the tensor
*/ */
void XTensor::SetData(const void * d, int num, int beg) void XTensor::SetData(const void* d, int num, int beg)
{ {
if (data == NULL || d ==NULL) if (data == NULL || d == NULL)
return; return;
CheckNTErrors(!isSparse, "TODO"); CheckNTErrors(!isSparse, "TODO");
...@@ -830,7 +830,7 @@ void XTensor::SetDataRand(DTYPE lower, DTYPE upper) ...@@ -830,7 +830,7 @@ void XTensor::SetDataRand(DTYPE lower, DTYPE upper)
// srand((unsigned)time(0)); // srand((unsigned)time(0));
DTYPE variance = upper - lower; DTYPE variance = upper - lower;
void * d = NULL; void* d = NULL;
if (dataType == X_FLOAT) { if (dataType == X_FLOAT) {
d = new float[unitNum]; d = new float[unitNum];
for (int i = 0; i < unitNum; i++) { for (int i = 0; i < unitNum; i++) {
...@@ -868,12 +868,12 @@ double GaussRand(DTYPE mean, DTYPE standardDeviation) ...@@ -868,12 +868,12 @@ double GaussRand(DTYPE mean, DTYPE standardDeviation)
double z; double z;
double pi = 3.141592654; double pi = 3.141592654;
if (phase == 0){ if (phase == 0) {
u = (rand() + 1.0) / (RAND_MAX + 1.0); u = (rand() + 1.0) / (RAND_MAX + 1.0);
v = (rand() + 1.0) / (RAND_MAX + 1.0); v = (rand() + 1.0) / (RAND_MAX + 1.0);
z = sqrt(-2.0 * log(u))* sin(2.0 * pi * v); z = sqrt(-2.0 * log(u)) * sin(2.0 * pi * v);
} }
else{ else {
z = sqrt(-2.0 * log(u)) * cos(2.0 * pi * v); z = sqrt(-2.0 * log(u)) * cos(2.0 * pi * v);
} }
...@@ -894,7 +894,7 @@ void XTensor::SetDataRandn(DTYPE mean, DTYPE standardDeviation) ...@@ -894,7 +894,7 @@ void XTensor::SetDataRandn(DTYPE mean, DTYPE standardDeviation)
return; return;
// srand((unsigned)time(0)); // srand((unsigned)time(0));
void * d = NULL; void* d = NULL;
if (dataType == X_FLOAT) { if (dataType == X_FLOAT) {
d = new float[unitNum]; d = new float[unitNum];
for (int i = 0; i < unitNum; i++) { for (int i = 0; i < unitNum; i++) {
...@@ -927,7 +927,7 @@ set tensor items with an array of offsets ...@@ -927,7 +927,7 @@ set tensor items with an array of offsets
>> value - value for the data items >> value - value for the data items
>> num - number of the data items >> num - number of the data items
*/ */
void XTensor::SetDataBatched(MTYPE * offsets, DTYPE value, int num) void XTensor::SetDataBatched(MTYPE* offsets, DTYPE value, int num)
{ {
_SetDataWithOffset(this, offsets, value, num); _SetDataWithOffset(this, offsets, value, num);
} }
...@@ -938,7 +938,7 @@ set tensor items with an array of values ...@@ -938,7 +938,7 @@ set tensor items with an array of values
>> values - value for each data item >> values - value for each data item
>> num - number of the data items >> num - number of the data items
*/ */
void XTensor::SetDataBatchedWithValues(MTYPE * offsets, void * values, int num) void XTensor::SetDataBatchedWithValues(MTYPE* offsets, void* values, int num)
{ {
_SetDataWithOffsetAndValue(this, offsets, values, num); _SetDataWithOffsetAndValue(this, offsets, values, num);
} }
...@@ -973,9 +973,9 @@ DTYPE XTensor::Get(int offset) const ...@@ -973,9 +973,9 @@ DTYPE XTensor::Get(int offset) const
CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!"); CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!");
CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!"); CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!");
CheckNTErrors(denseRatio == 1.0F, "Only dense tensors are supported in Get(offset)."); CheckNTErrors(denseRatio == 1.0F, "Only dense tensors are supported in Get(offset).");
DTYPE * address = (DTYPE*)data + offset; DTYPE* address = (DTYPE*)data + offset;
return ToCPU(devID, address); return ToCPU(devID, address);
} }
...@@ -985,25 +985,25 @@ get the pointer to a cell ...@@ -985,25 +985,25 @@ get the pointer to a cell
>> size - size of index >> size - size of index
<< return - pointer to the cell << return - pointer to the cell
*/ */
void * XTensor::GetCell(int index[], int size) const void* XTensor::GetCell(int index[], int size) const
{ {
CheckNTErrors((size == order), "Illegal index!"); CheckNTErrors((size == order), "Illegal index!");
int offset = index[0]; int offset = index[0];
for(int i = 1; i < size; ++i){ for (int i = 1; i < size; ++i) {
CheckNTErrors((index[i] < dimSize[i]), "Index is out of range!"); CheckNTErrors((index[i] < dimSize[i]), "Index is out of range!");
offset = offset * dimSize[i] + index[i]; offset = offset * dimSize[i] + index[i];
} }
if(isSparse){ if (isSparse) {
DTYPE value; DTYPE value;
void * p; void* p;
if(BinarySearch(offset, value, p)) if (BinarySearch(offset, value, p))
return (char*)p + sizeof(int); return (char*)p + sizeof(int);
else else
return NULL; return NULL;
} }
else{ else {
return ((char*)data) + offset * unitSize; return ((char*)data) + offset * unitSize;
} }
} }
...@@ -1018,7 +1018,7 @@ DTYPE XTensor::Get0D() const ...@@ -1018,7 +1018,7 @@ DTYPE XTensor::Get0D() const
CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type."); CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type.");
int dims[1] = {0}; int dims[1] = {0};
void * value = GetCell(dims, 0); void* value = GetCell(dims, 0);
return ToCPU(devID, value); return ToCPU(devID, value);
} }
...@@ -1035,7 +1035,7 @@ DTYPE XTensor::Get1D(int i) const ...@@ -1035,7 +1035,7 @@ DTYPE XTensor::Get1D(int i) const
CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type."); CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type.");
int dims[1] = {i}; int dims[1] = {i};
void * value = GetCell(dims, 1); void* value = GetCell(dims, 1);
return ToCPU(devID, value); return ToCPU(devID, value);
} }
...@@ -1054,7 +1054,7 @@ DTYPE XTensor::Get2D(int ni, int mi) const ...@@ -1054,7 +1054,7 @@ DTYPE XTensor::Get2D(int ni, int mi) const
CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type."); CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type.");
int dims[2] = {ni, mi}; int dims[2] = {ni, mi};
void * value = GetCell(dims, 2); void* value = GetCell(dims, 2);
return ToCPU(devID, value); return ToCPU(devID, value);
} }
...@@ -1067,14 +1067,14 @@ get the value of a cell in a 3d tensor ...@@ -1067,14 +1067,14 @@ get the value of a cell in a 3d tensor
*/ */
DTYPE XTensor::Get3D(int d0, int d1, int d2) const DTYPE XTensor::Get3D(int d0, int d1, int d2) const
{ {
CheckNTErrors((order == 3), "Cannot get a 2d cell for a tensor whose order is not 3!"); CheckNTErrors((order == 3), "Cannot get a 3d cell for a tensor whose order is not 3!");
CheckNTErrors((d0 >= 0 && d0 < dimSize[0]), "dimension 0 is out of range!"); CheckNTErrors((d0 >= 0 && d0 < dimSize[0]), "dimension 0 is out of range!");
CheckNTErrors((d1 >= 0 && d1 < dimSize[1]), "dimension 1 is out of range!"); CheckNTErrors((d1 >= 0 && d1 < dimSize[1]), "dimension 1 is out of range!");
CheckNTErrors((d2 >= 0 && d2 < dimSize[2]), "dimension 2 is out of range!"); CheckNTErrors((d2 >= 0 && d2 < dimSize[2]), "dimension 2 is out of range!");
CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type."); CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in default type.");
int dims[3] = {d0, d1, d2}; int dims[3] = {d0, d1, d2};
void * value = GetCell(dims, 3); void* value = GetCell(dims, 3);
return ToCPU(devID, value); return ToCPU(devID, value);
} }
...@@ -1089,9 +1089,9 @@ int XTensor::GetInt(int offset) const ...@@ -1089,9 +1089,9 @@ int XTensor::GetInt(int offset) const
CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!"); CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!");
CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!"); CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!");
CheckNTErrors(denseRatio == 1.0F, "Only dense tensors are supported in Get(offset)."); CheckNTErrors(denseRatio == 1.0F, "Only dense tensors are supported in Get(offset).");
int * address = (int*)data + offset; int* address = (int*)data + offset;
return ToCPUInt(devID, address); return ToCPUInt(devID, address);
} }
...@@ -1105,7 +1105,7 @@ int XTensor::Get0DInt() const ...@@ -1105,7 +1105,7 @@ int XTensor::Get0DInt() const
CheckNTErrors(dataType == X_INT, "The tensor is not in int type."); CheckNTErrors(dataType == X_INT, "The tensor is not in int type.");
int dims[1] = {0}; int dims[1] = {0};
void * value = GetCell(dims, 0); void* value = GetCell(dims, 0);
return ToCPUInt(devID, value); return ToCPUInt(devID, value);
} }
...@@ -1122,7 +1122,7 @@ int XTensor::Get1DInt(int i) const ...@@ -1122,7 +1122,7 @@ int XTensor::Get1DInt(int i) const
CheckNTErrors(dataType == X_INT, "The tensor is not in int type."); CheckNTErrors(dataType == X_INT, "The tensor is not in int type.");
int dims[1] = {i}; int dims[1] = {i};
void * value = GetCell(dims, 1); void* value = GetCell(dims, 1);
return ToCPUInt(devID, value); return ToCPUInt(devID, value);
} }
...@@ -1133,7 +1133,7 @@ get the value of a cell in a 2d tensor in int type ...@@ -1133,7 +1133,7 @@ get the value of a cell in a 2d tensor in int type
>> mi - column index >> mi - column index
<< return - value of cell(ni, mi) in int << return - value of cell(ni, mi) in int
*/ */
int XTensor::Get2DInt(int ni, int mi) const int XTensor::Get2DInt(int ni, int mi) const
{ {
CheckNTErrors(order == 2, "Cannot get a 2d cell for a tensor whose order is not 2!"); CheckNTErrors(order == 2, "Cannot get a 2d cell for a tensor whose order is not 2!");
CheckNTErrors(ni >= 0 && ni < dimSize[0], "dimension 0 is out of range!"); CheckNTErrors(ni >= 0 && ni < dimSize[0], "dimension 0 is out of range!");
...@@ -1141,7 +1141,7 @@ get the value of a cell in a 2d tensor in int type ...@@ -1141,7 +1141,7 @@ get the value of a cell in a 2d tensor in int type
CheckNTErrors(dataType == X_INT, "The tensor is not in default type."); CheckNTErrors(dataType == X_INT, "The tensor is not in default type.");
int dims[2] = {ni, mi}; int dims[2] = {ni, mi};
void * value = GetCell(dims, 2); void* value = GetCell(dims, 2);
return ToCPUInt(devID, value); return ToCPUInt(devID, value);
} }
...@@ -1155,14 +1155,14 @@ get the value of a cell in a 3d tensor in int type ...@@ -1155,14 +1155,14 @@ get the value of a cell in a 3d tensor in int type
*/ */
int XTensor::Get3DInt(int d0, int d1, int d2) const int XTensor::Get3DInt(int d0, int d1, int d2) const
{ {
CheckNTErrors(order == 3, "Cannot get a 2d cell for a tensor whose order is not 3!"); CheckNTErrors(order == 3, "Cannot get a 3d cell for a tensor whose order is not 3!");
CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!"); CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!");
CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!"); CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!");
CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!"); CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!");
CheckNTErrors(dataType == X_INT, "The tensor is not in default type."); CheckNTErrors(dataType == X_INT, "The tensor is not in default type.");
int dims[3] = {d0, d1, d2}; int dims[3] = {d0, d1, d2};
void * value = GetCell(dims, 3); void* value = GetCell(dims, 3);
return ToCPUInt(devID, value); return ToCPUInt(devID, value);
} }
...@@ -1177,8 +1177,8 @@ DTYPE XTensor::GetInSparse(int i) const ...@@ -1177,8 +1177,8 @@ DTYPE XTensor::GetInSparse(int i) const
CheckNTErrors(i >= 0 && i < unitNum, "Index is out of range!"); CheckNTErrors(i >= 0 && i < unitNum, "Index is out of range!");
CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type."); CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type.");
char * d = (char*)data + sizeof(int); char* d = (char*)data + sizeof(int);
DTYPE * value = (DTYPE*)(d + (sizeof(int) + sizeof(DTYPE)) * i + sizeof(int)); DTYPE* value = (DTYPE*)(d + (sizeof(int) + sizeof(DTYPE)) * i + sizeof(int));
return ToCPU(devID, value); return ToCPU(devID, value);
} }
...@@ -1193,9 +1193,9 @@ int XTensor::GetKeyInSparse(int i) const ...@@ -1193,9 +1193,9 @@ int XTensor::GetKeyInSparse(int i) const
CheckNTErrors(i >= 0 && i < unitNum, "Index is out of range!"); CheckNTErrors(i >= 0 && i < unitNum, "Index is out of range!");
CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type."); CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type.");
char * d = (char*)data + sizeof(int); char* d = (char*)data + sizeof(int);
int * key = (int*)(d + (sizeof(int) + sizeof(DTYPE)) * i); int* key = (int*)(d + (sizeof(int) + sizeof(DTYPE)) * i);
return ToCPUInt(devID, key); return ToCPUInt(devID, key);
} }
...@@ -1222,7 +1222,7 @@ bool XTensor::Set(DTYPE value, int offset) ...@@ -1222,7 +1222,7 @@ bool XTensor::Set(DTYPE value, int offset)
CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!"); CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!");
CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!"); CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!");
DTYPE * d = (DTYPE*)data + offset; DTYPE* d = (DTYPE*)data + offset;
return SetToDevice(devID, d, value); return SetToDevice(devID, d, value);
} }
...@@ -1288,7 +1288,7 @@ set the value of a cell in a 3d tensor in default type ...@@ -1288,7 +1288,7 @@ set the value of a cell in a 3d tensor in default type
*/ */
bool XTensor::Set3D(DTYPE value, int d0, int d1, int d2) bool XTensor::Set3D(DTYPE value, int d0, int d1, int d2)
{ {
CheckNTErrors(order == 3, "Cannot get a 2d cell for a tensor whose order is not 3!"); CheckNTErrors(order == 3, "Cannot get a 3d cell for a tensor whose order is not 3!");
CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!"); CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!");
CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!"); CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!");
CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!"); CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!");
...@@ -1308,9 +1308,9 @@ bool XTensor::SetInt(int value, int offset) ...@@ -1308,9 +1308,9 @@ bool XTensor::SetInt(int value, int offset)
{ {
CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!"); CheckNTErrors(offset >= 0 && offset < unitNum, "Invalid index!");
CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!"); CheckNTErrors(data != NULL, "Cannot use an uninitialized tensor!");
int * d = (int*)data + offset; int* d = (int*)data + offset;
return SetToDeviceInt(devID, d, value); return SetToDeviceInt(devID, d, value);
} }
...@@ -1390,7 +1390,7 @@ set the integer value of a cell in a 3d tensor in default type ...@@ -1390,7 +1390,7 @@ set the integer value of a cell in a 3d tensor in default type
*/ */
bool XTensor::Set3DInt(int value, int d0, int d1, int d2) bool XTensor::Set3DInt(int value, int d0, int d1, int d2)
{ {
CheckNTErrors(order == 3, "Cannot get a 2d cell for a tensor whose order is not 3!"); CheckNTErrors(order == 3, "Cannot get a 3d cell for a tensor whose order is not 3!");
CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!"); CheckNTErrors(d0 >= 0 && d0 < dimSize[0], "dimension 0 is out of range!");
CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!"); CheckNTErrors(d1 >= 0 && d1 < dimSize[1], "dimension 1 is out of range!");
CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!"); CheckNTErrors(d2 >= 0 && d2 < dimSize[2], "dimension 2 is out of range!");
...@@ -1408,23 +1408,23 @@ increase the value of a cell in a 2d tensor ...@@ -1408,23 +1408,23 @@ increase the value of a cell in a 2d tensor
>> mi - column index >> mi - column index
<< return - succeeded or not << return - succeeded or not
*/ */
bool XTensor::Add2D(DTYPE value, int ni, int mi) bool XTensor::Add2D(DTYPE value, int ni, int mi)
{ {
CheckNTErrors(ni >= 0 && ni < dimSize[0], "the row index is out of range!"); CheckNTErrors(ni >= 0 && ni < dimSize[0], "the row index is out of range!");
CheckNTErrors(mi >= 0 && mi < dimSize[1], "the column index is out of range!"); CheckNTErrors(mi >= 0 && mi < dimSize[1], "the column index is out of range!");
CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type."); CheckNTErrors(dataType == DEFAULT_DTYPE, "The tensor is not in default type.");
CheckNTErrors(isSparse == false, "TODO!"); CheckNTErrors(isSparse == false, "TODO!");
if(devID < 0){ if (devID < 0) {
DTYPE * p = (DTYPE*)data + ni * dimSize[1] + mi; DTYPE* p = (DTYPE*)data + ni * dimSize[1] + mi;
CheckNTErrors((p != NULL), "No data array is found!"); CheckNTErrors((p != NULL), "No data array is found!");
*p = *p + value; *p = *p + value;
return true; return true;
} }
else{ else {
int dims[2] = {ni, mi}; int dims[2] = {ni, mi};
return SetToDevice(devID, GetCell(dims, 2), Get2D(ni, mi) + value); return SetToDevice(devID, GetCell(dims, 2), Get2D(ni, mi) + value);
} }
...@@ -1433,24 +1433,24 @@ increase the value of a cell in a 2d tensor ...@@ -1433,24 +1433,24 @@ increase the value of a cell in a 2d tensor
/* get the number of non-zero elements (in a sparse tensor) */ /* get the number of non-zero elements (in a sparse tensor) */
int XTensor::GetNonzeroSize() const int XTensor::GetNonzeroSize() const
{ {
if(!isSparse){ if (!isSparse) {
XPRINT(1, stderr, "WARNING! Counting non-zero elements in a dense tensor might be slow!\n"); XPRINT(1, stderr, "WARNING! Counting non-zero elements in a dense tensor might be slow!\n");
CheckNTErrors(devID < 0, "TODO"); CheckNTErrors(devID < 0, "TODO");
if(dataType == DEFAULT_DTYPE){ if (dataType == DEFAULT_DTYPE) {
int count = 0; int count = 0;
for(int i = 0; i < unitNum; i++){ for (int i = 0; i < unitNum; i++) {
DTYPE value = *(DTYPE*)((char*)data + i * sizeof(DTYPE)); DTYPE value = *(DTYPE*)((char*)data + i * sizeof(DTYPE));
if(value == 0) if (value == 0)
count++; count++;
} }
return count; return count;
} }
else{ else {
ShowNTErrors("TODO!"); ShowNTErrors("TODO!");
return -1; return -1;
} }
} }
else{ else {
/* return the head of the tuple list */ /* return the head of the tuple list */
return unitNumNonZero; return unitNumNonZero;
} }
...@@ -1481,7 +1481,7 @@ set the tensor as "variable" ...@@ -1481,7 +1481,7 @@ set the tensor as "variable"
void XTensor::SetVarFlag(bool myIsVar) void XTensor::SetVarFlag(bool myIsVar)
{ {
isVar = myIsVar; isVar = myIsVar;
if(isVar) if (isVar)
SetGradFlag(true); SetGradFlag(true);
} }
...@@ -1493,11 +1493,11 @@ resize a tensor with a specified tensor size ...@@ -1493,11 +1493,11 @@ resize a tensor with a specified tensor size
>> myDenseRatio - how often an element has non-zero value >> myDenseRatio - how often an element has non-zero value
<< return - succeeded or not << return - succeeded or not
*/ */
bool XTensor::Resize(const int myOrder, const int * myDimSize, bool XTensor::Resize(const int myOrder, const int* myDimSize,
const TENSOR_DATA_TYPE myDataType, const float myDenseRatio) const TENSOR_DATA_TYPE myDataType, const float myDenseRatio)
{ {
/* free old mem */ /* free old mem */
if(data != NULL){ if (data != NULL) {
if (mem == NULL) if (mem == NULL)
XMemFree(devID, data); XMemFree(devID, data);
else else
...@@ -1513,11 +1513,11 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1513,11 +1513,11 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
bool filledData = true; bool filledData = true;
bool zeroData = false; bool zeroData = false;
for(int i = 0; i < order; i++){ for (int i = 0; i < order; i++) {
dimSize[i] = abs(myDimSize[i]); dimSize[i] = abs(myDimSize[i]);
if(myDimSize[i] < 0) if (myDimSize[i] < 0)
filledData = false; filledData = false;
if(myDimSize[i] == 0) if (myDimSize[i] == 0)
zeroData = true; zeroData = true;
unitNum *= dimSize[i]; unitNum *= dimSize[i];
} }
...@@ -1528,17 +1528,17 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1528,17 +1528,17 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
dataType = myDataType; dataType = myDataType;
unitSize = GetUnitSize(dataType); unitSize = GetUnitSize(dataType);
if(myDataType != DEFAULT_DTYPE) if (myDataType != DEFAULT_DTYPE)
isDefaultDType = false; isDefaultDType = false;
else else
isDefaultDType = true; isDefaultDType = true;
if(zeroData){ if (zeroData) {
unitNum = 0; unitNum = 0;
return false; return false;
} }
if(isSparse){ if (isSparse) {
/* /*
for sparse matrices, we use a list of tuple (key, value), for sparse matrices, we use a list of tuple (key, value),
ordered by key. Take a (2-dimensional) matrix as an example, ordered by key. Take a (2-dimensional) matrix as an example,
...@@ -1557,21 +1557,21 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1557,21 +1557,21 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
*/ */
int num = int(unitNum * denseRatio + 1); int num = int(unitNum * denseRatio + 1);
int tupleSize = sizeof(int)+sizeof(DTYPE); int tupleSize = sizeof(int) + sizeof(DTYPE);
int size = sizeof(int) + tupleSize*(num); int size = sizeof(int) + tupleSize * (num);
if(filledData){
int * d = NULL;
if(mem == NULL){ if (filledData) {
int* d = NULL;
if (mem == NULL) {
d = new int[size]; d = new int[size];
memset(d, 0, size); memset(d, 0, size);
} }
else{ else {
d = (int*)mem->Alloc(mem->devID, size); d = (int*)mem->Alloc(mem->devID, size);
} }
if(d == NULL) if (d == NULL)
return false; return false;
#if !defined(UNSAFE_BUT_FAST_MEM) #if !defined(UNSAFE_BUT_FAST_MEM)
...@@ -1581,11 +1581,11 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1581,11 +1581,11 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
} }
return true; return true;
} }
else{ else {
if(filledData){ if (filledData) {
/* allocate the new one */ /* allocate the new one */
if(mem == NULL){ if (mem == NULL) {
data = XMemAlloc(devID, unitNum * unitSize); data = XMemAlloc(devID, unitNum * unitSize);
#if defined(UNSAFE_BUT_FAST_MEM) #if defined(UNSAFE_BUT_FAST_MEM)
XMemSet(devID, data, 0, unitNum * unitSize); XMemSet(devID, data, 0, unitNum * unitSize);
#endif #endif
...@@ -1593,12 +1593,12 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1593,12 +1593,12 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
else else
data = (void*)mem->Alloc(mem->devID, unitNum * unitSize); data = (void*)mem->Alloc(mem->devID, unitNum * unitSize);
if(data == NULL) if (data == NULL)
return false; return false;
} }
#if !defined(UNSAFE_BUT_FAST_MEM) #if !defined(UNSAFE_BUT_FAST_MEM)
if(data != NULL) if (data != NULL)
XMem::SetZero(data, unitNum * unitSize, mem); XMem::SetZero(data, unitNum * unitSize, mem);
#endif #endif
return true; return true;
...@@ -1609,12 +1609,12 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize, ...@@ -1609,12 +1609,12 @@ bool XTensor::Resize(const int myOrder, const int * myDimSize,
resize a tensor by another resize a tensor by another
>> myTensor - tensor for reference >> myTensor - tensor for reference
*/ */
bool XTensor::Resize(const XTensor * myTensor) bool XTensor::Resize(const XTensor* myTensor)
{ {
denseRatio = myTensor->denseRatio; denseRatio = myTensor->denseRatio;
TENSOR_DATA_TYPE myDataType = myTensor->dataType; TENSOR_DATA_TYPE myDataType = myTensor->dataType;
if(myDataType != DEFAULT_DTYPE) if (myDataType != DEFAULT_DTYPE)
isDefaultDType = false; isDefaultDType = false;
else else
isDefaultDType = true; isDefaultDType = true;
...@@ -1630,54 +1630,54 @@ binary search to find an element in a sparse tensor ...@@ -1630,54 +1630,54 @@ binary search to find an element in a sparse tensor
it is the previous one if there is no hit it is the previous one if there is no hit
<< return - found it or not? << return - found it or not?
*/ */
bool XTensor::BinarySearch(int key, DTYPE &value, void * &position) const bool XTensor::BinarySearch(int key, DTYPE& value, void*& position) const
{ {
CheckNTErrors((isSparse), "A sparse tensor is required!"); CheckNTErrors((isSparse), "A sparse tensor is required!");
CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in the default type."); CheckNTErrors((dataType == DEFAULT_DTYPE), "The tensor is not in the default type.");
int * d = (int*)data; int* d = (int*)data;
if(key < 0 || *d == 0){ if (key < 0 || *d == 0) {
value = 0; value = 0;
position = NULL; position = NULL;
return false; return false;
} }
int low = 0; int low = 0;
int high = *d - 1; int high = *d - 1;
int last = -1; int last = -1;
bool ok = false; bool ok = false;
int * k = NULL; int* k = NULL;
int headSize = sizeof(int); int headSize = sizeof(int);
int tupleSize = sizeof(int)+sizeof(DTYPE); int tupleSize = sizeof(int) + sizeof(DTYPE);
char * p = (char*)data + headSize; char* p = (char*)data + headSize;
while (low <= high){ while (low <= high) {
int mid = low + (high-low)/2; int mid = low + (high - low) / 2;
k = (int*)(p + tupleSize * mid); k = (int*)(p + tupleSize * mid);
if (*k == key){ if (*k == key) {
ok = true; ok = true;
high = mid -1; high = mid - 1;
break; break;
}
else if(*k > key){
high = mid -1;
} }
else{ else if (*k > key) {
low = mid +1; high = mid - 1;
}
else {
low = mid + 1;
last = mid; last = mid;
} }
} }
if(ok){ if (ok) {
DTYPE * p = (DTYPE*)((char*)k + sizeof(int)); DTYPE* p = (DTYPE*)((char*)k + sizeof(int));
value = *p; value = *p;
position = k; position = k;
return true; return true;
} }
else{ else {
value = 0; value = 0;
if(last == -1) if (last == -1)
position = NULL; position = NULL;
else else
position = (char*)data + headSize + tupleSize * last; position = (char*)data + headSize + tupleSize * last;
...@@ -1693,12 +1693,12 @@ dump data to a file ...@@ -1693,12 +1693,12 @@ dump data to a file
>> beg - the first item id >> beg - the first item id
>> verbose - verbose level >> verbose - verbose level
*/ */
void XTensor::Dump(FILE * file, const char * label, const int n, const int beg, const int verbose) void XTensor::Dump(FILE* file, const char* label, const int n, const int beg, const int verbose)
{ {
if (verbose > verboseLevel) if (verbose > verboseLevel)
return; return;
void * d = data; void* d = data;
bool isNewData = false; bool isNewData = false;
#ifdef USE_CUDA #ifdef USE_CUDA
...@@ -1716,7 +1716,7 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg, ...@@ -1716,7 +1716,7 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg,
num *= dimSize[i]; num *= dimSize[i];
num = int(num * denseRatio + 1); num = int(num * denseRatio + 1);
int tupleSize = sizeof(int) + sizeof(DTYPE); int tupleSize = sizeof(int) + sizeof(DTYPE);
int size = sizeof(int) + tupleSize*(num); int size = sizeof(int) + tupleSize * (num);
d = new char[size]; d = new char[size];
memset(d, 0, size); memset(d, 0, size);
...@@ -1730,8 +1730,8 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg, ...@@ -1730,8 +1730,8 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg,
if (label != NULL) if (label != NULL)
fprintf(file, "%s ", label); fprintf(file, "%s ", label);
if(isInit){ if (isInit) {
fprintf(file, "order=%d dimsize=", order); fprintf(file, "order=%d dimsize=", order);
if (order == 0) { if (order == 0) {
fprintf(file, "%d,", dimSize[0]); fprintf(file, "%d,", dimSize[0]);
...@@ -1742,21 +1742,21 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg, ...@@ -1742,21 +1742,21 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg,
fprintf(file, ","); fprintf(file, ",");
} }
} }
else{ else {
fprintf(file, "order=-1 dimsize=-1"); fprintf(file, "order=-1 dimsize=-1");
} }
fprintf(file, " dtype=%s dense=%f\n", GetDataTypeName(dataType), denseRatio); fprintf(file, " dtype=%s dense=%f\n", GetDataTypeName(dataType), denseRatio);
if(!isInit){ if (!isInit) {
fprintf(file, "NULL"); fprintf(file, "NULL");
} }
if (!isSparse) { if (!isSparse) {
if (dataType == DEFAULT_DTYPE) { if (dataType == DEFAULT_DTYPE) {
int end = MIN(n > 0 ? beg + n : beg + unitNum, unitNum); int end = MIN(n > 0 ? beg + n : beg + unitNum, unitNum);
for(int i = beg; i < end; i++){ for (int i = beg; i < end; i++) {
DTYPE f = ((DTYPE*)d)[i]; DTYPE f = ((DTYPE*)d)[i];
if(i == beg) if (i == beg)
fprintf(file, "%e", f); fprintf(file, "%e", f);
else else
fprintf(file, " %e", f); fprintf(file, " %e", f);
...@@ -1765,9 +1765,9 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg, ...@@ -1765,9 +1765,9 @@ void XTensor::Dump(FILE * file, const char * label, const int n, const int beg,
} }
else if (dataType == X_INT) { else if (dataType == X_INT) {
int end = MIN(n > 0 ? beg + n : beg + unitNum, unitNum); int end = MIN(n > 0 ? beg + n : beg + unitNum, unitNum);
for(int i = beg; i < end; i++){ for (int i = beg; i < end; i++) {
int f = ((int*)d)[i]; int f = ((int*)d)[i];
if(i == beg) if (i == beg)
fprintf(file, "%d", f); fprintf(file, "%d", f);
else else
fprintf(file, " %d", f); fprintf(file, " %d", f);
...@@ -1807,7 +1807,7 @@ dump data to a file ...@@ -1807,7 +1807,7 @@ dump data to a file
>> beg - the first item id >> beg - the first item id
>> verbose - verbose level >> verbose - verbose level
*/ */
void XTensor::Dump(const XTensor * tensor, FILE * file, const char * label, const int n, const int beg, const int verbose) void XTensor::Dump(const XTensor* tensor, FILE* file, const char* label, const int n, const int beg, const int verbose)
{ {
XTensor a(tensor->order, tensor->dimSize, tensor->dataType, tensor->denseRatio, tensor->devID, tensor->mem); XTensor a(tensor->order, tensor->dimSize, tensor->dataType, tensor->denseRatio, tensor->devID, tensor->mem);
_CopyValues(tensor, &a); _CopyValues(tensor, &a);
...@@ -1839,7 +1839,7 @@ read data from a file ...@@ -1839,7 +1839,7 @@ read data from a file
>> file - where to load the data >> file - where to load the data
>> label - label of the tensor >> label - label of the tensor
*/ */
void XTensor::Read(FILE * file, const char * label) void XTensor::Read(FILE* file, const char* label)
{ {
char typeName[32] = ""; char typeName[32] = "";
char dimSizeName[128] = ""; char dimSizeName[128] = "";
...@@ -1858,7 +1858,7 @@ void XTensor::Read(FILE * file, const char * label) ...@@ -1858,7 +1858,7 @@ void XTensor::Read(FILE * file, const char * label)
fgetc(file); fgetc(file);
if (fscanf(file, "order=%d dimsize=%s dtype=%s dense=%f", if (fscanf(file, "order=%d dimsize=%s dtype=%s dense=%f",
&dimNum, dimSizeName, typeName, &dRatio) < 4) { &dimNum, dimSizeName, typeName, &dRatio) < 4) {
ShowNTErrors("Incorrect format when reading the tensor!"); ShowNTErrors("Incorrect format when reading the tensor!");
} }
...@@ -1872,7 +1872,7 @@ void XTensor::Read(FILE * file, const char * label) ...@@ -1872,7 +1872,7 @@ void XTensor::Read(FILE * file, const char * label)
int o = 0; int o = 0;
bool sameSize = true; bool sameSize = true;
char * p = dimSizeName; char* p = dimSizeName;
while (*p != 0) { while (*p != 0) {
while (*p == ' ' || *p == '\t') while (*p == ' ' || *p == '\t')
p++; p++;
...@@ -1896,14 +1896,14 @@ void XTensor::Read(FILE * file, const char * label) ...@@ -1896,14 +1896,14 @@ void XTensor::Read(FILE * file, const char * label)
if (!sameSize || dRatio > denseRatio || GetDataType(typeName) != dataType) if (!sameSize || dRatio > denseRatio || GetDataType(typeName) != dataType)
Resize(dimNum, dims, GetDataType(typeName), dRatio); Resize(dimNum, dims, GetDataType(typeName), dRatio);
void * dataBuf = XMemAlloc(-1, GetDataSizeInChar()); void* dataBuf = XMemAlloc(-1, GetDataSizeInChar());
void * dataBackup = data; void* dataBackup = data;
data = dataBuf; data = dataBuf;
if (!isSparse) { if (!isSparse) {
if (dataType == DEFAULT_DTYPE) { if (dataType == DEFAULT_DTYPE) {
for (int i = 0; i < unitNum; i++) { for (int i = 0; i < unitNum; i++) {
DTYPE * f = ((DTYPE*)data) + i; DTYPE* f = ((DTYPE*)data) + i;
if (fscanf(file, "%e", f) < 1) { if (fscanf(file, "%e", f) < 1) {
ShowNTErrors("Incorrect tensor format!"); ShowNTErrors("Incorrect tensor format!");
} }
...@@ -1956,13 +1956,13 @@ void XTensor::BinaryRead(FILE* file, size_t offset) ...@@ -1956,13 +1956,13 @@ void XTensor::BinaryRead(FILE* file, size_t offset)
fseek(file, offset, 0); fseek(file, offset, 0);
switch (dataType) { switch (dataType) {
case X_INT: { case X_INT: {
int * d = new int[unitNum]; int* d = new int[unitNum];
fread(d, sizeof(int), unitNum, file); fread(d, sizeof(int), unitNum, file);
SetData(d, unitNum); SetData(d, unitNum);
delete[] d; delete[] d;
} }
default: { default: {
float * d = new float[unitNum]; float* d = new float[unitNum];
fread(d, sizeof(float), unitNum, file); fread(d, sizeof(float), unitNum, file);
SetData(d, unitNum); SetData(d, unitNum);
delete[] d; delete[] d;
...@@ -1974,7 +1974,7 @@ void XTensor::BinaryRead(FILE* file, size_t offset) ...@@ -1974,7 +1974,7 @@ void XTensor::BinaryRead(FILE* file, size_t offset)
flush the data to the target device flush the data to the target device
>> targetMem - memory pool on the target device >> targetMem - memory pool on the target device
*/ */
void XTensor::FlushToMem(XMem * targetMem) void XTensor::FlushToMem(XMem* targetMem)
{ {
if (targetMem == NULL) if (targetMem == NULL)
return; return;
...@@ -1987,7 +1987,7 @@ void XTensor::FlushToMem(XMem * targetMem) ...@@ -1987,7 +1987,7 @@ void XTensor::FlushToMem(XMem * targetMem)
CudaCPUToGPUFlush(&l, targetMem->devID, targetMem); CudaCPUToGPUFlush(&l, targetMem->devID, targetMem);
} }
else if (mem != targetMem) { else if (mem != targetMem) {
void * tmpData = targetMem->Alloc(targetMem->devID, GetDataSizeInChar()); void* tmpData = targetMem->Alloc(targetMem->devID, GetDataSizeInChar());
XMemCopy(tmpData, targetMem->devID, data, devID, GetDataSizeInChar()); XMemCopy(tmpData, targetMem->devID, data, devID, GetDataSizeInChar());
data = tmpData; data = tmpData;
mem = targetMem; mem = targetMem;
...@@ -2016,24 +2016,24 @@ allocate the memory space of the tensor (in the global memory) ...@@ -2016,24 +2016,24 @@ allocate the memory space of the tensor (in the global memory)
>> myMem - the memory pool we are using >> myMem - the memory pool we are using
>> useBuf - indicates whether we use the buffer in the memory pool >> useBuf - indicates whether we use the buffer in the memory pool
*/ */
void XTensor::AllocateData(XTensor * tensor, XMem * myMem, bool useBuf) void XTensor::AllocateData(XTensor* tensor, XMem* myMem, bool useBuf)
{ {
if(tensor == NULL) if (tensor == NULL)
return; return;
if(myMem == NULL){ if (myMem == NULL) {
if(tensor->data != NULL) if (tensor->data != NULL)
FreeData(tensor, NULL, false); FreeData(tensor, NULL, false);
tensor->data = XMemAlloc(tensor->devID, tensor->GetDataSizeInChar()); tensor->data = XMemAlloc(tensor->devID, tensor->GetDataSizeInChar());
tensor->isInGlobalMem = true; tensor->isInGlobalMem = true;
} }
else{ else {
CheckNTErrors((tensor->data == NULL), "Cannot renew the space for the tensor"); CheckNTErrors((tensor->data == NULL), "Cannot renew the space for the tensor");
if(useBuf){ if (useBuf) {
tensor->data = myMem->AllocBuf(tensor->devID, tensor->GetDataSizeInChar()); tensor->data = myMem->AllocBuf(tensor->devID, tensor->GetDataSizeInChar());
tensor->isInGlobalMem = false; tensor->isInGlobalMem = false;
} }
else{ else {
tensor->data = myMem->AllocGlobal(tensor->devID, tensor->GetDataSizeInChar()); tensor->data = myMem->AllocGlobal(tensor->devID, tensor->GetDataSizeInChar());
tensor->isInGlobalMem = true; tensor->isInGlobalMem = true;
} }
...@@ -2048,16 +2048,16 @@ free the memory space of the tensor (in the global memory) ...@@ -2048,16 +2048,16 @@ free the memory space of the tensor (in the global memory)
>> myMem - the memory pool we are using >> myMem - the memory pool we are using
>> useBuf - indicates whether we use the buffer in the memory pool >> useBuf - indicates whether we use the buffer in the memory pool
*/ */
void XTensor::FreeData(XTensor * tensor, XMem * myMem, bool useBuf) void XTensor::FreeData(XTensor* tensor, XMem* myMem, bool useBuf)
{ {
if(tensor == NULL) if (tensor == NULL)
return; return;
if(myMem == NULL){ if (myMem == NULL) {
XMemFree(tensor->devID, tensor->data); XMemFree(tensor->devID, tensor->data);
} }
else{ else {
if(tensor->isInGlobalMem) if (tensor->isInGlobalMem)
myMem->ReleaseGlobal(tensor->devID, tensor->data); myMem->ReleaseGlobal(tensor->devID, tensor->data);
else else
myMem->ReleaseBuf(tensor->devID, tensor->GetDataSizeInChar()); myMem->ReleaseBuf(tensor->devID, tensor->GetDataSizeInChar());
...@@ -2068,27 +2068,27 @@ void XTensor::FreeData(XTensor * tensor, XMem * myMem, bool useBuf) ...@@ -2068,27 +2068,27 @@ void XTensor::FreeData(XTensor * tensor, XMem * myMem, bool useBuf)
} }
/* overloading of the plus-sign */ /* overloading of the plus-sign */
XTensor operator+ (const DTYPE shift, const XTensor &tensor) XTensor operator+ (const DTYPE shift, const XTensor& tensor)
{ {
return ScaleAndShift(tensor, 1, shift); return ScaleAndShift(tensor, 1, shift);
} }
/* overloading of the minus-sign */ /* overloading of the minus-sign */
XTensor operator- (const DTYPE shift, const XTensor &tensor) XTensor operator- (const DTYPE shift, const XTensor& tensor)
{ {
return ScaleAndShift(tensor, 1, -shift); return ScaleAndShift(tensor, 1, -shift);
} }
/* overloading of the multiply-sign */ /* overloading of the multiply-sign */
XTensor operator* (const DTYPE scale, const XTensor &tensor) XTensor operator* (const DTYPE scale, const XTensor& tensor)
{ {
return ScaleAndShift(tensor, scale, 0); return ScaleAndShift(tensor, scale, 0);
} }
/* overloading of the division-sign */ /* overloading of the division-sign */
XTensor operator/ (const DTYPE scale, const XTensor &tensor) XTensor operator/ (const DTYPE scale, const XTensor& tensor)
{ {
return ScaleAndShift(tensor, (DTYPE)1/scale, 0); return ScaleAndShift(tensor, (DTYPE)1.0F / scale, 0);
} }
} /* end of the nts (NiuTrans.Tensor) namespace */ } /* end of the nts (NiuTrans.Tensor) namespace */
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论